当前位置: X-MOL 学术Nat. Hazards › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Zoning map for drought prediction using integrated machine learning models with a nomadic people optimization algorithm
Natural Hazards ( IF 3.3 ) Pub Date : 2020-08-19 , DOI: 10.1007/s11069-020-04180-9
Sedigheh Mohamadi , Saad Sh. Sammen , Fatemeh Panahi , Mohammad Ehteram , Ozgur Kisi , Amir Mosavi , Ali Najah Ahmed , Ahmed El-Shafie , Nadhir Al-Ansari

The modelling of drought is of utmost importance for the efficient management of water resources. This article used the adaptive neuro-fuzzy interface system (ANFIS), multilayer perceptron (MLP), radial basis function neural network (RBFNN), and support vector machine (SVM) models to forecast meteorological droughts in Iran. The spatial–temporal pattern of droughts in Iran was also found using recorded observation data from 1980 to 2014. A nomadic people algorithm (NPA) was utilized to train the ANFIS, MLP, RBFNN, and SVM models. Additionally, the NPA was benchmarked against the bat algorithm, salp swarm algorithm, and krill algorithm (KA). The hybrid ANFIS, MLP, RBFNN, and SVM models were used to forecast the 3-month standardized precipitation index. New evolutionary algorithms were utilized to improve the convergence speed of the soft computing models and their accuracy. First, random stations, namely, in Azarbayjan (northwest Iran), Khouzestan (southwest Iran), Khorasan (northeast Iran), and Sistan and Balouchestan (southeast Iran) were selected for the testing of the models. According to the results obtained from the Azarbayjan station, the Nash–Sutcliffe efficiency (NSE) was 0.93, 0.86, 0.85, and 0.83 for the ANFIS–NPA, MLP–NPA, RBFNN–NPA, and SVM–NPA models, respectively. For Sistan and Baloucehstan, the results indicated the superiority of the ANFIS–NPA model, followed by the MLP–NPA model, compared to the RBFNN–NPA and SVM–NPA models, and suggested that the hybrid models performed better than the standalone MLP, RBFNN, ANFIS, and SVM models. The second aim of the study was to capture the relationship between large-scale climate signals and drought indices by using a wavelet coherence analysis. The general results indicated that the NPA and wavelet coherence analysis are useful tools for modelling drought indices.



中文翻译:

使用带有游牧民优化算法的集成机器学习模型进行干旱预测的分区图

干旱建模对于水资源的有效管理至关重要。本文使用自适应神经模糊接口系统(ANFIS),多层感知器(MLP),径向基函数神经网络(RBFNN)和支持向量机(SVM)模型来预测伊朗的气象干旱。使用记录的1980年至2014年的观测数据还发现了伊朗的干旱时空格局。一个游牧民族算法(NPA)被用于训练ANFIS,MLP,RBFNN和SVM模型。此外,NPA还以蝙蝠算法,小群算法和磷虾算法(KA)为基准。ANFIS,MLP,RBFNN和SVM混合模型用于预测3个月标准化降水指数。利用新的进化算法来提高软计算模型的收敛速度及其准确性。首先,选择随机站点,即阿扎尔巴扬(伊朗西北部),Khouzestan(伊朗西南部),Khorasan(伊朗东北部)以及Sistan和Balouchestan(伊朗东南部)进行模型测试。根据从Azarbayjan站获得的结果,ANFIS-NPA,MLP-NPA,RBFNN-NPA和SVM-NPA模型的Nash-Sutcliffe效率(NSE)分别为0.93、0.86、0.85和0.83。对于Sistan和Baloucehstan,结果表明,与RBFNN-NPA和SVM-NPA模型相比,ANFIS-NPA模型,其次是MLP-NPA模型具有优越性,并表明混合模型的性能优于独立MLP, RBFNN,ANFIS和SVM模型。该研究的第二个目的是通过小波相干分析来捕获大规模气候信号与干旱指数之间的关系。总体结果表明,NPA和小波相干分析是建模干旱指数的有用工具。

更新日期:2020-08-19
down
wechat
bug